返回
Peak response regularization for localization
DOI:10.1038/s41598-024-65770-2.png)
摘要
En 中文
Deep convolutional neural networks approaches often assume that the feature response has a Gaussian distribution with target-centered peak response, which can be used to guide the target location and classification. Nevertheless, such an assumption is implausible when there is progressive interference from other targets and/or background noise, which produces sub-peaks on the tracking response map and causes model drift. In this paper, we propose a feature response regularization approach for sub-peak response suppression and peak response enforcement and aim to handle progressive interference systematically. Our approach, referred to as Peak Response Regularization (PRR), applies simple-yet-efficient method to aggregate and align discriminative features, which convert local extremal response in discrete feature space to extremal response in continuous space, which enforces the localization and representation capability of convolutional features. Experiments on human pose detection, object detection, object tracking, and image classification demonstrate that PRR improves the performance of image tasks with a negligible computational cost.
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.9
论文数:
28.2W
被引数:
83.5W
机构
引用论文
A Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection用于交通标志检测的具有多尺度注意力和不平衡样本的级联r-cnn
IEEE ACCESS
IF3.6
Energy-Efficient Robot Configuration and Motion Planning Using Genetic Algorithm and Particle Swarm Optimization基于遗传算法和粒子群算法的节能机器人配置和运动规划
Energies
IF0
Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系?
Deep convolutional neural network based medical image classification for disease diagnosis
JOURNAL OF BIG DATA
IF6.4

